Re: [PATCH v5 4/8] x86/mm/tlb: Flush remote and local TLBs concurrently

On Feb 16, 2021, at 4:10 AM, Peter Zijlstra [off-list ref] wrote:

On Tue, Feb 09, 2021 at 02:16:49PM -0800, Nadav Amit wrote:

quoted

@@ -816,8 +821,8 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,

	 * doing a speculative memory access.
	 */
	if (info->freed_tables) {
-		smp_call_function_many(cpumask, flush_tlb_func,
-			       (void *)info, 1);
+		on_each_cpu_cond_mask(NULL, flush_tlb_func, (void *)info, true,
+				      cpumask);
	} else {
		/*
		 * Although we could have used on_each_cpu_cond_mask(),

@@ -844,14 +849,15 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,

			if (tlb_is_not_lazy(cpu))
				__cpumask_set_cpu(cpu, cond_cpumask);
		}
-		smp_call_function_many(cond_cpumask, flush_tlb_func, (void *)info, 1);
+		on_each_cpu_cond_mask(NULL, flush_tlb_func, (void *)info, true,
+				      cpumask);
	}
}

Surely on_each_cpu_mask() is more appropriate? There the compiler can do
the NULL propagation because it's on the same TU.

--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c

@@ -821,8 +821,7 @@ STATIC_NOPV void native_flush_tlb_multi(

	 * doing a speculative memory access.
	 */
	if (info->freed_tables) {
-		on_each_cpu_cond_mask(NULL, flush_tlb_func, (void *)info, true,
-				      cpumask);
+		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
	} else {
		/*
		 * Although we could have used on_each_cpu_cond_mask(),

@@ -849,8 +848,7 @@ STATIC_NOPV void native_flush_tlb_multi(

			if (tlb_is_not_lazy(cpu))
				__cpumask_set_cpu(cpu, cond_cpumask);
		}
-		on_each_cpu_cond_mask(NULL, flush_tlb_func, (void *)info, true,
-				      cpumask);
+		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
	}
}